lmstudio-community/functiongemma-270m-it-MLX-bf16
TEXT GENERATIONConcurrency Cost:1Model Size:0.3BQuant:BF16Ctx Length:32kPublished:Dec 18, 2025License:gemmaArchitecture:Transformer Cold
The functiongemma-270m-it-MLX-bf16 model, developed by Google, is a 0.3 billion parameter instruction-tuned variant of the Gemma architecture. This specific version is optimized for Apple Silicon using MLX quantization, making it efficient for local inference on compatible hardware. It is designed for function-calling tasks, enabling applications to interact with external tools and APIs.
Loading preview...
Overview
This model is functiongemma-270m-it, a 0.3 billion parameter instruction-tuned model from Google, specifically optimized for Apple Silicon. It leverages the MLX framework for efficient local inference, provided by the LM Studio team. The model is based on the original bfloat16 version of functiongemma-270m-it.
Key Capabilities
- Function Calling: Designed to understand and generate function calls, enabling interaction with external tools and APIs.
- Apple Silicon Optimization: Quantized using MLX, making it highly efficient for deployment and inference on Apple's M-series chips.
- Compact Size: With 0.3 billion parameters, it offers a balance between performance and resource efficiency.
Good For
- Developers building applications on Apple Silicon that require efficient, local function-calling capabilities.
- Integrating AI models with external services and tools through structured function calls.
- Experimenting with smaller, specialized models for specific task automation on compatible hardware.